Student Projects

DNA can be used for storage of information the same way the genetic codes of most living entities, including humans, are stored in their DNA. There are several advantages behind such an approach, such as a much higher storage density, long term preservation capability and better energy efficiency. The underlying information in DNA is represented in a quaternary code (AGCT) instad of a binary code (01). This calls for completely new approaches to efficiently code information in a DNA compatible manner. 

The goal of this project is to study alternatives approaches proposed in the state of the art to store informaiton in DNA and to come up with an end-to-end image compression simulator by taking advantage of publicly accessible implementations.  

The following tasks should be performed during the project:

• Study the relevant state of the art relevant in DNA storage and coding.
• Identify existing source code for DNA storage and analyse them.
• Design and implement a simulator of image compression for DNA storage based on state of the art implementations  
• Analyse the performance of the simulator.

Requirements: Basic knowledge of signal and image processing. Good programming skills.

Contact: Touradj Ebrahimi

Group: Prof. Touradj Ebrahimi

Suitable for: Bachelor Semester Project, Master Semester Project or Master Thesis in Electrical Engineering, Communication Systems, Computer Science, Digital Humanities, Mechanical Engineering, Micro Engineering, Management of Technology and/or equivalent.

Number of students: One

Due to the increasing spread of doctored or synthetic contents on the Internet and their impact on the dissemination of fake news over social networks, detecting manipulated content has become a major challenge in both academic and professional communities. Major companies have joined forces to organize challenges with the goal of helping in the process of creating widely accessible tools and solutions to detect malicious modifications of multimedia contents.

One of the most important and recent actions was the Deepfake Detection Challenge organized by Facebook and Microsoft, with the involvement of many academic research groups. The organizers hoped that this challenge would result in new technologies for detecting AI-generated videos which can later be used on social networking platforms and/or by journalists. This illustrates the major concerns of large companies about the danger of AI-assisted content manipulations. 

In this project, we tackle the deepfake detection problem by training several convolutional neural networks (CNNs) in a supervised fashion. Finally, the ensembling of different trained CNNs will be studied.

In particular, two main objectives will be pursued in this project. The first aims at finding existing and publicly available deepfake datasets. The second aims at training deep neural networks using the above datasets for the task of deepfake detection. The following tasks should be performed by the student:

• Review the state of the art deepfake detection methods 
• Study the state of the art deepfake creation methods and find/generate their corresponding dataset which can further be used for training of CNNs.
• Run/Adapt/Create a program to detect deepfake images and videos
• Investigate the most common performance metrics
• Assess the performance of the trained models against several datasets
• Document the code and write a report on the project

Requirements: Good skills in Python programming. Background in deep learning and image processing.

Contact: Touradj Ebrahimi, Enes Eray Demirtas

Group: Prof. Touradj Ebrahimi

Suitable for: Master Semester Project or Master Thesis in Electrical Engineering, Communication Systems, Computer Science, or equivalent.

Number of students: One

Recently, public interest in privacy protection has increased dramatically. However, there is a general believe that protection of privacy will restrict online benefits of users. Therefore, protection of privacy in such a way that does not distract online habits of people is needed. This project focuses on visual privacy protection in images. Specifically, the intention of the project is to develop a mobile (iOS or Android platform) application that would be able to obfuscate personal visual information in an image in a secure and recoverable way and share images via online social networks in a secure way.

The following tasks should be performed during the project:

• Research and review the existing visual privacy protection tools, as well as the way to share and manage secure content in social networks.
• Design an app on smartphone with iOS or Android operating system. An iPhone or Android phone will be provided by the lab.
• Minimal requirements of the app include:
  • Implementation of security processing (e.g. scrambling) for images on the mobile side.
  • Multi-region processing on image using touch screen.
• Implementation of a simple key management system.

Requirements: Basic knowledge of image processing, good programming skills in Objective-C, experience in iOS or Android development.

Contact: Touradj Ebrahimi, Enes Eray Demirtas

Group: Prof. Touradj Ebrahimi

Suitable for: Bachelor Project or Master Semester Project in Electrical Engineering, Communication Systems, or Computer Science.

Number of students: One.

Detecting misinformation in images is not only a question of whether the content has been manipulated. An entirely authentic photograph can be reused to illustrate an event it has nothing to do with, and in such cases a Web search may confirm that the described event genuinely took place without establishing that the submitted image depicts it. Recent work on content-based factuality assessment within the JPEG Trust framework has shown that this contextual verification step is the main bottleneck of current automated fact-checking pipelines: while miscaptioned content is detected with reasonable accuracy, out-of-context content remains largely undetected when no information about the earlier use of the specific image is available.

The goal of this project is to build a component that searches for earlier appearances of a submitted image on the Web and recovers the date, location, and event associated with them, and to measure how much this additional information improves the detection of out-of-context misinformation.

An existing fact-checking pipeline and the corresponding evaluation setup will be provided, so that the work can focus on the retrieval component itself.

The following tasks should be performed during the project:

• Study the relevant state of the art in reverse image search, including perceptual hashing and image similarity based on visual features.
• Compare a small number of candidate tools and approaches, such as open-source visual search engines and similarity search over a locally built image collection.
• Implement a module that, given an image, returns candidate earlier appearances together with their source, date, and description.
• Connect the module to the provided pipeline and evaluate the effect on relevant publicly available multimodal misinformation datasets, in particular on out-of-context cases.
• Analyse a selection of successful and failed cases and describe why the approach works or fails.
• Document the code and write a report on the project.

Requirements: Good programming skills in Python. Basic knowledge of image processing. Familiarity with deep learning is an asset but not required.

Contact: Touradj Ebrahimi, Enes Eray Demirtas

Group: Prof. Touradj Ebrahimi

Suitable for: Bachelor Semester Project, Master Semester Project or Master Thesis in Electrical Engineering, Communication Systems, Computer Science, or equivalent. The scope of the project is adapted to the level of study.

Number of students: One.

JPEG Trust (ISO/IEC 21617) provides a framework in which trust-related information about a media asset is expressed through Trust Indicators and then interpreted, according to the needs of a given application, by a Trust Profile that produces a Trust Report. Provenance, authenticity, metadata, watermarking, and attribution are already covered by this architecture. Content-based factuality, meaning whether the story accompanying an image is supported by evidence and consistent with the image itself, has recently been proposed as an additional and complementary trust dimension. So far, however, this proposal remains conceptual: how such information should be stored inside a media asset, and how it should be interpreted alongside the other indicators, has not yet been implemented.

The goal of this project is to define a concrete way of representing factuality information in a JPEG Trust compatible manner, to implement the tools that generate and read it, and to show how different applications can interpret it differently. Structured outputs from an existing multimodal fact-checking system are available as input to the work.

The following tasks should be performed during the project:

• Study the main concepts of JPEG Trust and the structured outputs of an existing multimodal fact-checking system.
• Design the information to be represented in a prototype Factuality Trust Indicator.
• Implement software for generating and reading the proposed factuality representation.
• Develop simple Trust Profile examples combining factuality with other trust information such as provenance, authenticity, or metadata, and generate the corresponding Trust Reports.
• Evaluate the prototype on representative media examples and analyse how factuality contributes to the resulting trust assessment.
• Document the code and write a report on the project.

Requirements: Good programming skills. Basic knowledge of image and file formats. Interest in standardization and in metadata formats such as JSON and XMP.

Contact: Touradj Ebrahimi, Enes Eray Demirtas

Group: Prof. Touradj Ebrahimi

Suitable for: Bachelor Semester Project, Master Semester Project or Master Thesis in Electrical Engineering, Communication Systems, Computer Science, or equivalent. The scope of the project is adapted to the level of study.

Number of students: One.